Arrange citations

Author: andrewdalpino

docs/neural-network/activation-functions/silu.md

@@ -14,5 +14,4 @@ $activationFunction = new SiLU();
 ```
 
 ### References
->- S. Elwing et al. (2017). Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning.
->- P. Ramachandran er al. (2017). Swish: A Self-gated Activation Function.
+[^1]: S. Elwing et al. (2017). Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning.

docs/neural-network/hidden-layers/swish.md

@@ -17,4 +17,5 @@ $layer = new Swish(new Constant(1.0));
 ```
 
 ## References
-[^1]: P. Ramachandran et al. (2017). Searching for Activation Functions.
+[^1]: P. Ramachandran er al. (2017). Swish: A Self-gated Activation Function.
+[^2]: P. Ramachandran et al. (2017). Searching for Activation Functions.

src/Graph/Nodes/Decision.php

@@ -14,7 +14,7 @@
 interface Decision extends BinaryNode
 {
     /**
-     * Return the impurity of the labels as a result of the decision.
+     * Return the impurity of the labels within the node.
      *
      * @return float
      */

src/NeuralNet/ActivationFunctions/SiLU.php

@@ -13,9 +13,8 @@
  * the [Sigmoid](sigmoid.md) activation function acting as a self-gating mechanism.
  *
  * References:
- * [1] S. Elwing et al. (2017). Sigmoid-Weighted Linear Units for Neural Network Function
- * Approximation in Reinforcement Learning.
- * [2] P. Ramachandran et al. (2017). Swish: A Self-gated Activation Function.
+ * [1] S. Elwing et al. (2017). Sigmoid-Weighted Linear Units for Neural Network Function Approximation in
+ * Reinforcement Learning.
  *
  * @category    Machine Learning
  * @package     Rubix/ML

src/NeuralNet/Layers/Swish.php

@@ -19,7 +19,8 @@
  * *beta* parameter allows each activation function in the layer to tailor its output to the training set by
  * interpolating between the linear function and ReLU.
  *
- * [1] P. Ramachandran et al. (2017). Searching for Activation Functions.
+ * [1] P. Ramachandran et al. (2017). Swish: A Self-gated Activation Function.
+ * [2] P. Ramachandran et al. (2017). Searching for Activation Functions.
  *
  * @category    Machine Learning
  * @package     Rubix/ML